用于科学史、科学哲学与科学社会学的大语言模型：阐释性应用、方法论挑战与批判视角
Large Language Models for History, Philosophy, and Sociology of Science: Interpretive Uses, Methodological Challenges, and Critical Perspectives
AI总结：
该研究探讨大语言模型在科学史、科学哲学与科学社会学（HPSS）领域的应用，分析其作为认识论基础设施的特性、适配策略与优劣，提出整合LLMs进HPSS的四点原则，强调LLMs应辅助而非替代阐释方法。
摘要：
本文探讨大语言模型（large language models, LLMs）作为研究工具在科学史、科学哲学与科学社会学（history, philosophy, and sociology of science, HPSS）领域的应用。LLMs在处理非结构化文本、根据语境推断含义方面表现出色，提供了新的应用可能性，也对计算方法与阐释方法之间长期存在的分野提出了挑战。这为强调阐释方法论、将意义视为语境依赖、模糊且具有历史情境性的HPSS领域同时带来了机遇与挑战。我们认为，HPSS不仅具备独特优势可以从LLMs的能力中获益，也有能力审视其认识论假设与基础设施层面的影响。为此，我们首先为非技术读者量身打造了LLM架构与训练范式的简明入门指南。我们将LLMs定位为并非中立的工具，而是编码了关于意义、语境与相似性的假设的认识论基础设施，这些假设受其训练数据、架构与使用模式的制约。随后，我们考察了经LLMs增强的计算技术（如数据结构化、模式检测、动态过程建模）如何应用于支持HPSS的阐释性研究。我们的分析对比了全上下文模型与生成式模型，概述了领域适配与任务适配策略（例如持续预训练、微调、检索增强生成），并评估了它们各自在HPSS阐释性研究中的优势与局限。最后，我们总结了将LLMs整合进HPSS的四点经验：（1）模型选择涉及阐释层面的权衡；（2）LLM素养是基础；（3）HPSS必须定义自身的基准与语料库；（4）LLMs应增强而非替代阐释方法。
英文摘要：
This paper explores the use of large language models (LLMs) as research tools in the history, philosophy, and sociology of science (HPSS). LLMs are remarkably effective at processing unstructured text and inferring meaning from context, offering new affordances that challenge long-standing divides between computational and interpretive methods. This raises both opportunities and challenges for HPSS, which emphasizes interpretive methodologies and understands meaning as context-dependent, ambiguous, and historically situated. We argue that HPSS is uniquely positioned not only to benefit from LLMs' capabilities but also to interrogate their epistemic assumptions and infrastructural implications. To this end, we first offer a concise primer on LLM architectures and training paradigms tailored to non-technical readers. We frame LLMs not as neutral tools but as epistemic infrastructures that encode assumptions about meaning, context, and similarity, conditioned by their training data, architecture, and patterns of use. We then examine how computational techniques enhanced by LLMs, such as structuring data, detecting patterns, and modeling dynamic processes, can be applied to support interpretive research in HPSS. Our analysis compares full-context and generative models, outlines strategies for domain and task adaptation (e.g., continued pretraining, fine-tuning, and retrieval-augmented generation), and evaluates their respective strengths and limitations for interpretive inquiry in HPSS. We conclude with four lessons for integrating LLMs into HPSS: (1) model selection involves interpretive trade-offs; (2) LLM literacy is foundational; (3) HPSS must define its own benchmarks and corpora; and (4) LLMs should enhance, not replace, interpretive methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
